Garment Recovery with Shape and Deformation Priors

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Ren, Dumery, Corentin, Guillard, Benoît, Fua, Pascal
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916156432973824
author Li, Ren
Dumery, Corentin
Guillard, Benoît
Fua, Pascal
author_facet Li, Ren
Dumery, Corentin
Guillard, Benoît
Fua, Pascal
contents While modeling people wearing tight-fitting clothing has made great strides in recent years, loose-fitting clothing remains a challenge. We propose a method that delivers realistic garment models from real-world images, regardless of garment shape or deformation. To this end, we introduce a fitting approach that utilizes shape and deformation priors learned from synthetic data to accurately capture garment shapes and deformations, including large ones. Not only does our approach recover the garment geometry accurately, it also yields models that can be directly used by downstream applications such as animation and simulation.
format Preprint
id arxiv_https___arxiv_org_abs_2311_10356
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Garment Recovery with Shape and Deformation Priors
Li, Ren
Dumery, Corentin
Guillard, Benoît
Fua, Pascal
Computer Vision and Pattern Recognition
While modeling people wearing tight-fitting clothing has made great strides in recent years, loose-fitting clothing remains a challenge. We propose a method that delivers realistic garment models from real-world images, regardless of garment shape or deformation. To this end, we introduce a fitting approach that utilizes shape and deformation priors learned from synthetic data to accurately capture garment shapes and deformations, including large ones. Not only does our approach recover the garment geometry accurately, it also yields models that can be directly used by downstream applications such as animation and simulation.
title Garment Recovery with Shape and Deformation Priors
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.10356